# ENVS278 Chapter Notes - Chapter 21: Null Hypothesis, 2Degrees, Location Test

## Document Summary

The natural display for comparing two groups is box plots that are placed side by side should always start with them when comparing groups: helps to identify outliers. The population model parameter of interest is the difference between the mean batter lifetime of the two brands 1 2. The statistical interest is the difference in the two observed means y-bar1 y-bar2. Start by building the confidence interval need to know the standard deviation and its sampling model then we can build confidence interval and find p-values. We know that for independent random quantities the variance of their difference is the sum of their variances, var(y-x)= var(y)+var(x: sd (y-bar1-y-bar2) = [var(y-bar1 ) var (y-bar2)] However since we do not know the true standard deviations we will use estimates to get the standard error: se(y-bar1-y-bar2)= [(s2. Can use the standard error to see how big the difference really is (example p. 601)